Related papers: A General Upper Bound for Unsupervised Domain Adap…

In theory, the success of unsupervised domain adaptation (UDA) largely relies on domain gap estimation. However, for source free UDA, the source domain data can not be accessed during adaptation, which poses great challenge of measuring the…

The objective of unsupervised domain adaptation is to leverage features from a labeled source domain and learn a classifier for an unlabeled target domain, with a similar but different data distribution. Most deep learning approaches to…

In this paper, we explore bounds on the expected risk when using deep neural networks for supervised classification from an information theoretic perspective. Firstly, we introduce model risk and fitting error, which are derived from…

Unsupervised domain translation has recently achieved impressive performance with Generative Adversarial Network (GAN) and sufficient (unpaired) training data. However, existing domain translation frameworks form in a disposable way where…

We study the problem of choosing algorithm hyper-parameters in unsupervised domain adaptation, i.e., with labeled data in a source domain and unlabeled data in a target domain, drawn from a different input distribution. We follow the…

Domain generalisation (DG) methods address the problem of domain shift, when there is a mismatch between the distributions of training and target domains. Data augmentation approaches have emerged as a promising alternative for DG. However,…

Domain adaptation (DA) addresses the real-world image classification problem of discrepancy between training (source) and testing (target) data distributions. We propose an unsupervised DA method that considers the presence of only…

Domain adaptation has been a fundamental technology for transferring knowledge from a source domain to a target domain. The key issue of domain adaptation is how to reduce the distribution discrepancy between two domains in a proper way…

The well known domain shift issue causes model performance to degrade when deployed to a new target domain with different statistics to training. Domain adaptation techniques alleviate this, but need some instances from the target domain to…

Unsupervised domain adaptation (UDA) aims to improve the prediction performance in the target domain under distribution shifts from the source domain. The key principle of UDA is to minimize the divergence between the source and the target…

The primary objective of domain adaptation methods is to transfer knowledge from a source domain to a target domain that has similar but different data distributions. Thus, in order to correctly classify the unlabeled target domain samples,…

The ability to build a model on a source task and subsequently adapt such model on a new target task is a pervasive need in many astronomical applications. The problem is generally known as transfer learning in machine learning, where…

Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation. However, as deep features eventually transition from general to specific along the network, the…

A central problem in unsupervised domain adaptation is determining what to transfer from labeled source domains to an unlabeled target domain. To handle high-dimensional observations (e.g., images), a line of approaches use deep learning to…

The ability to generalize learned representations across significantly different visual domains, such as between real photos, clipart, paintings, and sketches, is a fundamental capacity of the human visual system. In this paper, different…

Unsupervised Domain Adaptation (UDA) is quite challenging due to the large distribution discrepancy between the source domain and the target domain. Inspired by diffusion models which have strong capability to gradually convert data…

Although deep networks have significantly increased the performance of visual recognition methods, it is still challenging to achieve the robustness across visual domains that is necessary for real-world applications. To tackle this issue,…

Getting deep convolutional neural networks to perform well requires a large amount of training data. When the available labelled data is small, it is often beneficial to use transfer learning to leverage a related larger dataset (source) in…

Although achieving remarkable progress, it is very difficult to induce a supervised classifier without any labeled data. Unsupervised domain adaptation is able to overcome this challenge by transferring knowledge from a labeled source…

The accuracy of deep learning (e.g., convolutional neural networks) for an image classification task critically relies on the amount of labeled training data. Aiming to solve an image classification task on a new domain that lacks labeled…